aif-build-automation

Analyze project and generate or enhance build automation file (Makefile, Taskfile.yml, Justfile, Magefile.go). If a build file already exists, improves it by adding missing targets and best practices. Use when user says "generate makefile", "create taskfile", "add justfile", "setup mage", or "build automation".

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced skill body with concrete commands and validation checkpoints. Its main weakness is redundancy of the JVM catalog rules and minor reference-path/structure gaps.

Suggestions

Consolidate the JVM task-name catalog into one authoritative table and reference it from §2.2, Step 5, and Customization instead of restating the rules in each place.

Trim the Step 0 skill-context override explanation to a single concise statement of the 'skill-context rule wins' principle rather than repeating it 3-4 times.

Add a post-write verification checkpoint (e.g. run `make help` / `task --list` / `just --list`) to Step 6 or the Quality Checks to close the validation loop.

Reconcile reference paths (use 'references/BEST-PRACTICES.md' to match the bundle) and ensure the referenced templates/ directory ships with the skill.

Dimension	Reasoning	Score
Conciseness	Avoids basic-concept padding, but the JVM catalog/task-name rules are restated in §2.2, the Step 5 table, the Step 5 JVM bullet, and the Customization section, and the skill-context 'rule wins' principle is repeated 3-4 times in Step 0 — noticeable redundancy that could be tightened.	3 / 5
Actionability	Provides concrete Glob/Grep patterns, exact Gradle/Maven command tables, a template-selection matrix, and a fixed target-name catalog — copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	Clear Steps 0-7 sequence with a pre-write Quality Checks checklist and an enforcement feedback loop (verify→fix→present), but lacks an explicit post-write run-verification checkpoint.	4 / 5
Progressive Disclosure	References are clearly signaled and BEST-PRACTICES/SUMMARY-FORMAT/DOC-INTEGRATION exist in the bundle, but body paths use 'skills/aif-build-automation/references/…' while the bundle uses 'references/…', and the referenced templates/ directory is absent from the bundle.	4 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that explicitly states capabilities and concrete trigger phrases for each supported tool. It clearly answers both 'what' and 'when' with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain (Makefile, Taskfile.yml, Justfile, Magefile.go) and several concrete actions — 'Analyze project', 'generate or enhance', 'improves it by adding missing targets and best practices' — but coverage is not exhaustive.	4 / 5
Completeness	Explicitly answers both what ('Analyze project and generate or enhance build automation file…') and when ('Use when user says…') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases ('generate makefile', 'create taskfile', 'add justfile', 'setup mage', 'build automation') across all four tools, though synonyms and file extensions are not exhaustively listed.	4 / 5
Distinctiveness Conflict Risk	Clear niche — build automation for four specifically named tools — with distinct trigger phrases, giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (615 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-build-automation/SKILL.md
Commit: e144f95

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.